Primaries

We will be looking at the Primary results in Iowa and New Hampshire.

library(tigris)
library(leaflet)
library(magrittr)
library(dplyr)

## 
## Attaching package: 'dplyr'
## 
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## 
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(acs)

## 
## Attaching package: 'acs'
## 
## The following object is masked from 'package:dplyr':
## 
##     combine
## 
## The following object is masked from 'package:base':
## 
##     apply

library(ggplot2)
library(plotly)

## 
## Attaching package: 'plotly'
## 
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## 
## The following object is masked from 'package:graphics':
## 
##     layout

#we'll focus mostly on iowa:
primary <- read.csv("PrimaryResults.csv", stringsAsFactors = FALSE)

iowa.counties <- counties(state = "IA") #spatial data using tigris

bernie.ia <- filter(primary, State == "Iowa", Party == "Democrat",
                    Candidate == "Bernie Sanders")

merge <- geo_join(iowa.counties, bernie.ia, "NAME", "County")

#map of percentage voting for bernie
pal <- colorNumeric(c("Blues"), domain = NULL)
popup = paste0(merge$County, " County", "<br>", 
"Percentage voting for Bernie: ", 100*merge$FractionVotes, "%")

leaflet() %>%
    addProviderTiles("CartoDB.Positron") %>%
    addPolygons(data = merge, fillOpacity = .6,
                color = "white", weight = 1,
                smoothFactor = .2,
                fillColor = ~pal(FractionVotes),
                popup = popup) %>% 
    addLegend(pal = pal,values = merge$FractionVotes*100,
              title = "Percentage Voting <br> for Bernie")

#more interesting stuff:
#general results
primary %>%
    group_by(Party, Candidate) %>%
    summarise(mean(FractionVotes)*100)

## Source: local data frame [15 x 3]
## Groups: Party [?]
## 
##         Party       Candidate mean(FractionVotes) * 100
##         (chr)           (chr)                     (dbl)
## 1    Democrat  Bernie Sanders               48.77144858
## 2    Democrat Hillary Clinton               50.41203766
## 3    Democrat Martin O'Malley                0.78787879
## 4    Democrat     Uncommitted                0.03030303
## 5  Republican      Ben Carson                9.92848188
## 6  Republican   Carly Fiorina                2.20954354
## 7  Republican  Chris Christie                1.77187240
## 8  Republican    Donald Trump               27.68094663
## 9  Republican        Jeb Bush                3.15197746
## 10 Republican     John Kasich                2.66997771
## 11 Republican     Marco Rubio               18.12764629
## 12 Republican   Mike Huckabee                2.41677604
## 13 Republican       Rand Paul                3.40994830
## 14 Republican   Rick Santorum                0.99565467
## 15 Republican        Ted Cruz               28.26308140

#winner by county
winner <- primary %>% 
            group_by(Party, State, County) %>% 
            summarize(candidate = Candidate[which.max(FractionVotes)],
                                            vote = max(FractionVotes))
#hsould work for any state and party:

party <- "Republican"
state <- "Iowa"

counties <- counties(state = state)

final.df <- filter(winner, Party == party)

merge <- geo_join(counties, final.df, "NAME", "County")


#map of winner by county by party in IOWA
pal = colorFactor(c("dark red","dark green", "blue"), domain = merge$candidate)

leaflet() %>% 
    addProviderTiles("CartoDB.Positron") %>% 
    addPolygons(data = merge, weight = 1, color = "white",
                smoothFactor = 0.2,
                fillColor = ~pal(merge$candidate), fillOpacity = .7) %>% 
    addLegend(pal = pal, value = merge$candidate,
              title = "Winner by County")

#I'd like to look at educational level and income versus who voted for whom:
#acs package:
geo <- geo.make(state = "IA", county = "*")
income <- acs.fetch(table.name = "Per Capita Income", col.names = "pretty",
                    geography = geo)

#income@acs.colnames use this to see the colnames

income.df <- data_frame(County = income@geography$NAME,
                        income = income@estimate[,c("Per Capita Income:  Per capita income in the past 12 months (in 2011 inflation-adjusted dollars) ")]
) #use the dplyr data_frame version to keep the strings

income.df$County[1] # we need the first word

## [1] "Adair County, Iowa"

income.df$County <- sapply(income.df$County, function(x) 
    {strsplit(x, " ", fixed = TRUE)[[1]][1]})

winner.rep <- filter(winner, Party == "Republican")
winner.rep.ia<- inner_join(winner.rep, income.df, by = "County")

winner.rep.ia %>%
    group_by(candidate) %>%
    summarize(mean(income))

## Source: local data frame [3 x 2]
## 
##      candidate mean(income)
##          (chr)        (dbl)
## 1 Donald Trump     24280.51
## 2  Marco Rubio     29388.00
## 3     Ted Cruz     24384.75

#educational attainment:
#from the census fact finder
education <- read.csv("iowa_edu.csv", stringsAsFactors = FALSE)

college <- data_frame(County = education$GEO.display.label, 
                   college = education$HC01_EST_VC05)

college <- college[-1,]

college$County <- sapply(college$County, function(x) 
{strsplit(x, " ", fixed = TRUE)[[1]][1]})

winner.rep.ia <- inner_join(winner.rep.ia, college, by = "County")
winner.rep.ia$college <- as.numeric(winner.rep.ia$college)


ggplotly(qplot(x =  income, y = college, data = winner.rep.ia, 
               color = candidate))

# do a test to see if trump, cruz populations are similar.
#mayber permutation? or chi-squared

#let's look at democrats:
winner.dem <- filter(winner, Party == "Democrat")
winner.dem.ia <-inner_join(winner.dem, income.df, by = "County")

winner.dem.ia <- inner_join(winner.dem.ia, college, by = "County")
winner.dem.ia$college <- as.numeric(winner.dem.ia$college)

qplot(x =  income, y = college, data = winner.dem.ia, 
      color = candidate, size = .75) 

winner.dem.ia %>% 
    group_by(candidate) %>% 
    summarize(mean(college), mean(income))

## Source: local data frame [2 x 3]
## 
##         candidate mean(college) mean(income)
##             (chr)         (dbl)        (dbl)
## 1  Bernie Sanders      8.582353     24962.26
## 2 Hillary Clinton      7.063333     24410.15